Advancing Crops with AI and Data
Researchers are leveraging digital agriculture tools to enhance plant breeding, agronomy, and sustainability by enabling data-driven decisions.
At the forefront of this transformation is Dr. Keshav Singh and his team at AAFC's Lethbridge Research and Development Centre, who are using digital phenomics and remote sensing technologies to optimize productivity and reduce environmental impact.
Phenomics involves studying observable traits in plants and analyzing how genetics interact with environmental factors. Traditional research methods often require significant time and labour, while advanced techniques allow artificial intelligence to process large datasets efficiently. Cameras and AI-powered systems can quickly and accurately capture plant data, improving research outcomes and accelerating crop development.
Dr. Singh’s team is integrating digital phenomics with remote sensing technologies for Prairie field crops. They are developing advanced sensing systems that use optical, infrared, thermal, and laser technologies. These innovations create scalable data pipelines that turn raw information into actionable insights, helping identify desirable plant traits.
"Advanced technologies like remote sensing and phenomics tools are transforming Canadian agriculture by making crop breeding and agronomy more precise, efficient and resilient," said Singh.
Plant breeders seek traits such as seed size, plant height, and resistance to diseases and drought. Since breeding new crop varieties involves analyzing thousands of plants across multiple generations, digital tools help speed up this process. With climate change intensifying environmental challenges, faster identification of resilient traits is critical for food security.
Dr. Singh’s team is collaborating with researchers across Canada to study various parameters in cereal crops, including vegetation cover, flowering timelines, grain yield, and protein content. These digital tools assist wheat breeders in selecting climate-resilient, high-yielding varieties more efficiently.
Digital agriculture is also improving weed management and fertilizer optimization. Researchers are using AI models to study herbicide-resistant weeds and develop sustainable control methods. Other applications include enhancing dry bean breeding, mitigating root rot in peas, and optimizing nitrogen use in wheat and canola to reduce greenhouse gas emissions.
Dr. Singh and his team are leading efforts to integrate digital phenomics and remote sensing, driving innovation in plant breeding and sustainable crop management for future agricultural success.